2-3B Parameter LLMs — Page 84

med-record-audit-qwen2.5-3b-grpo

reasoning-gym-chain-sum-Qwen3-1.7B

Qwen2.5-3B-Base-Math-v2

incident-commander-qwen3-1.7b-grpo

cnk12_Main_fixed_SFTanchor_3B_step_5

qwen3_1.7B_Base_GRPO_Polaris_1000_steps

Phi-4-mini-instruct-mlx-fp16

math_model

Sinhala-Qwen3-v7500

math_model

Qwen2.5-3B-CrysReas-RL

Graph-Preflexor-3b_08012026

Qwen3_CPT_1.7B

Llama-3.2-3B-Instruct-HI-SynthDolly-r16alpha32-E3-S73

Llama_3_2_3B_Conversational_v7_SFT_10voicebot_loopcleaned

qwen2.5-3b-alpaca-id

Neuron-V1-3B-Instruct

supportlm-qwen2.5-3b

qwen2.5-3b-pgabl-ardhi-exp2_lr1e4_r16_s3000

Llama-3.2-3B-Indo-Finetuned

qwen3-1.7b-amr-20260705-0708

kim_graphRAG_longmemory_bank-v2

qwen2.5-3b-instruct-indonesia

AlphaMed-3B-instruct-rl

qwen25-3b-indo-ft

legal-chatbot-qwen2.5-3b-sft-id

Teacher_r14_train_gptmini_all7-Qwen2-5-3B-Instruct-seed51485

BALANCED_claude_max_max7_perblock35-Qwen2-5-3B-Instruct-seed88888888

BALANCED_Teacher_r14_train_gptmini-Qwen2-5-3B-Instruct-seed1010

Qwen3-1.7B-base-MED

Qwen3-ASR-Refiner-1.7B

tofu_Llama-3.2-3B-Instruct_forget05_WGA

tofu_Llama-3.2-3B-Instruct_forget10_UNDIAL

OneSQL-v0.2-Qwen-3B

Qwen2.5-3B-Instruct-Sheldon-SFT-v2-merged

Reliability-1.7B-final-brier-ckpt-900

llama-3.2-3b-michael-scott-merged

qwen2.5-vl-3b-ac-exp09-time-mgmt-world-model-stage1-lora-epoch3

qwen2.5-vl-3b-ac-exp09-time-mgmt-world-model-stage1-lora-epoch2

ForestFireVLM-3B

llama3b-llama8b-er-v102-jb-seed2-seed2-alpacaGPT4

Phi-3.5-mini-instruct-mlx-ft